AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Deep Contextual Attention for Human-Object Interaction Detection

Tiancai Wang, Rao Muhammad Anwer, Muhammad Haris Khan, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao, Jorma Laaksonen

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 146 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add context-aware appearance features (ablation)multi-stream HOI baseline · V-COCOmAP_role: 44.5 -> 46.0Improved
add contextual attention on top of context-aware appearance (ablation)multi-stream HOI baseline · V-COCOmAP_role: 46.0 -> 47.3Improved
add both context modules to the baseline (ablation)multi-stream HOI baseline · V-COCOmAP_role: 44.5 -> 47.3Improved
evaluate at a low IoU threshold (0.1) to isolate classification (ablation)Our Approach vs baseline · V-COCOmAP_role: 50.1 -> 53.5Improved
evaluate at a high IoU threshold (0.9) (ablation)Our Approach vs baseline · V-COCOmAP_role: 2.5 -> 2.8No clear effect
add context modules with VGG-16 backbone (ablation)multi-stream HOI baseline · V-COCOmAP_role: 42.0 -> 44.5Improved
add context modules with ResNet-101 backbone (ablation)multi-stream HOI baseline · V-COCOmAP_role: 45.0 -> 47.8Improved
use contextual attention approach instead of iCANiCAN · V-COCOmAP_role: 45.3 -> 47.3Improved
use contextual attention approach instead of iCANiCAN · HICO-DET Default fullmAP: 14.84 -> 16.24Improved
use contextual attention approach instead of iCANiCAN · HICO-DET Known Object fullmAP: 16.43 -> 17.73Improved
use contextual attention approach instead of iCANiCAN · HCVRD R@50top-1 accuracy: 33.8 -> 37.1Improved
add context modules (inference cost)baseline · interaction recognition timems per image: 111ms -> 130 millisecondsHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy